HiveNAS: Neural Architecture Search using Artificial Bee Colony Optimization

TL;DR

HiveNAS introduces a novel Artificial Bee Colony optimization approach for Neural Architecture Search, significantly improving search efficiency and outperforming existing swarm intelligence methods in neural network design.

Contribution

The paper presents HiveNAS, the first to apply Artificial Bee Colony optimization to NAS, demonstrating superior performance and efficiency over existing swarm-based methods.

Findings

HiveNAS outperforms state-of-the-art swarm intelligence NAS frameworks.

HiveNAS achieves faster search times with comparable or better accuracy.

Artificial Bee Colony optimization is viable for neural architecture search.

Abstract

The traditional Neural Network-development process requires substantial expert knowledge and relies heavily on intuition and trial-and-error. Neural Architecture Search (NAS) frameworks were introduced to robustly search for network topologies, as well as facilitate the automated development of Neural Networks. While some optimization approaches -- such as Genetic Algorithms -- have been extensively explored in the NAS context, other Metaheuristic Optimization algorithms have not yet been investigated. In this study, we evaluate the viability of Artificial Bee Colony optimization for Neural Architecture Search. Our proposed framework, HiveNAS, outperforms existing state-of-the-art Swarm Intelligence-based NAS frameworks in a fraction of the time.